Hello everyone,

I need to reproduce the sorting algorithm used in teams. 
On the attached screenshot you can see, that all files whose name starts from “_” or “#” go before “1” and all other files, but “-” is just ignored. I need to be sure, that my sorting reproducing will work the same as teams. Is there a clear explanation of how it works? Should I consider it as a bug in MS Teams?

​Hello everyone,I need to reproduce the sorting algorithm used in teams. On the attached screenshot you can see, that all files whose name starts from “_” or “#” go before “1” and all other files, but “-” is just ignored. I need to be sure, that my sorting reproducing will work the same as teams. Is there a clear explanation of how it works? Should I consider it as a bug in MS Teams?   Read More

​

While I am copying data from original page to another page using flow it show submitter name as my name. Since it needs to show who is the submitter previously in original page. could you help me on this to fix. PFA screenshot for your reference.

​While I am copying data from original page to another page using flow it show submitter name as my name. Since it needs to show who is the submitter previously in original page. could you help me on this to fix. PFA screenshot for your reference.    Read More

​

Hi,

We are using Project Server 2019. We came across an issue wherein a task got automatically deleted after the Actual Work was updated. We are not able to figure it out, how as tasks cannot be deleted if actuals are booked on it. How can i find the root cause of this issue. can i check it in the Project Server Queue or in the ULS Logs.

Regards,

Amit Wairkar

​Hi, We are using Project Server 2019. We came across an issue wherein a task got automatically deleted after the Actual Work was updated. We are not able to figure it out, how as tasks cannot be deleted if actuals are booked on it. How can i find the root cause of this issue. can i check it in the Project Server Queue or in the ULS Logs. Regards,Amit Wairkar  Read More

​

Hi all,

A week or two ago my Teams app updated and suddenly my camera didn’t work during a meeting anymore – just a camera icon with the line through it. Switching the camera off in the app then obviously only showed the profile pic as it should – switching it back on, laptop camera goes on (I see the light at the top of the laptop) but the camera Icon with the line through appears again.

The things I’ve done to try and find/fix this issue.

– checked camera permissions – Teams included in the list
– in app the laptop camera is selected
– device manager – camera drivers are up to date
– my system Windows 11 is up to date
– uninstalled and re-installed the Teams app 3 times with a laptop restart before and after each uninstall and reinstall – no change

Does anyone have any idea 

​Hi all,A week or two ago my Teams app updated and suddenly my camera didn’t work during a meeting anymore – just a camera icon with the line through it. Switching the camera off in the app then obviously only showed the profile pic as it should – switching it back on, laptop camera goes on (I see the light at the top of the laptop) but the camera Icon with the line through appears again.The things I’ve done to try and find/fix this issue. – checked camera permissions – Teams included in the list- in app the laptop camera is selected- device manager – camera drivers are up to date- my system Windows 11 is up to date- uninstalled and re-installed the Teams app 3 times with a laptop restart before and after each uninstall and reinstall – no changeDoes anyone have any idea   Read More

​

I am Sarita , Microsoft Learn Student Ambassador. In this guide, we’ll walk you through the steps to set up a chatbot using Open AI’s GPT-4o model that leverages Azure’s advanced language models. At the end, I have provided with a link to the repository to integrate the chatbot in your very own website.  

Building Your Own Chatbot with Azure OpenAI Capabilities 

What is Azure Open AI Service ? 

“Azure OpenAI Service provides REST API access to OpenAI’s powerful language models including GPT-4o, GPT-4o mini, GPT-4 Turbo with Vision, GPT-4, GPT-3.5-Turbo, and Embeddings model series. These models can be easily adapted to your specific task including but not limited to content generation, summarization, image understanding, semantic search, and natural language to code translation. Users can access the service through REST APIs, Python SDK, or our web-based interface in the Azure OpenAI Studio.”    – Microsoft Learn 

Prerequisites  

An Azure Account with Active Azure Subscription.  
Account on Azure Open AI Studio  

Understanding Key Terms 

Before diving into the setup, it’s essential to familiarize yourself with some key terms: 

Playground: A user-friendly interface that allows you to explore, prototype, and test AI assistants without any coding requirements. It’s perfect for iterating and experimenting with new ideas. 

Azure AI Services: A suite of tools and services that leverage artificial intelligence to help you build intelligent applications. 

Resource Group: A container that holds related Azure resources for management and billing. 

Keys and Endpoints: Security credentials and URLs that allow your applications to access Azure services. 

Model Deployment: The process of configuring and launching a specific AI model for use. 

System Message: Instructions provided to the AI model to guide its behaviour and response context. 

Prompt: The input you give to the AI model to elicit a specific response. 
Token : Tokens can be thought of as pieces of words. Before the API processes the request, the input is broken down into tokens. These tokens are not cut up exactly where the words start or end – tokens can include trailing spaces and even sub-words. Here are some helpful rules of thumb for understanding tokens in terms of lengths: 1 token ~= 4 chars in English,1 token ~= ¾ words ,100 tokens ~= 75 words.

Selecting the Right Model on Right Pricing  

Models 

Description 

GPT-4o & GPT-4o mini & GPT-4 Turbo 

The latest most capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. 

GPT-4 

A set of models that improve on GPT-3.5 and can understand and generate natural language and code. 

GPT-3.5 

A set of models that improve on GPT-3 and can understand and generate natural language and code. 

Embeddings 

A set of models that can convert text into numerical vector form to facilitate text similarity. 

DALL-E 

A series of models that can generate original images from natural language. 

Whisper 

A series of models in preview that can transcribe and translate speech to text. 

Text to speech (Preview) 

A series of models in preview that can synthesize text to speech. 

– Microsoft learn Open AI service 

Azure OpenAI Service offers two main pricing models for using its AI tools: Standard (On-Demand) and Provisioned Throughput Units (PTUs). Let’s understand both one by one: 

Standard (On-Demand) Pricing: 

You only pay for what you use.  
The cost is calculated based on the number of tokens processed, where tokens represent chunks of text (input and output). 
For each 1,000 tokens, there is a specific cost. For example, the more complex the model (like GPT-4), the higher the token cost. 
This model is flexible and works well if you’re unsure how much you’ll use the service or if you don’t need continuous access. 

Provisioned Throughput Units (PTUs): 

This model offers consistent performance with less waiting time and guarantees throughput. 
You pay a fixed hourly rate per PTU, so costs are predictable. 
There are additional costs for input and output tokens, but since PTUs provide faster and more stable access, this model is ideal for larger-scale usage or scenarios where latency matters. 
PTUs also have minimum scaling requirements (meaning you must buy a certain number of units to use the service at this level). 

Comparison: 

Standard (On-Demand): Pay only for tokens, ideal for small or variable usage. 
PTU: Fixed hourly rate + token costs, better for stable and high-volume tasks. 

Example (Why use GPT-4o as a student): 

GPT-4o has a lower cost per token compared to other models like GPT-4-Turbo. This makes it cost-effective for students or small-scale users, and it doesn’t include Price per PTU per Hour, unlike GPT-4-Turbo. 

Let’s Get Started 

Step 1: Create an Azure and Azure OpenAI Account –

To begin, you’ll need to set up an Azure account if you don’t already have one. Visit the Azure  and Azure Open AI websites to get started. 

Step 2: Create a New Resource Group 

Search for “Resource Group” in the Azure search box. 
Click on “Create” to start a new Resource Group. 
Fill in the required details: 

Subscription : Choose your Azure subscription. 
Resource Group Name : Give your group a unique name. 
Location : Select the Azure region that suits you. 

Click “Review + Create” and then “Create”. 
Wait a few minutes for the resource group to be established. 

Step 3: Create a New Azure OpenAI Resource 

Search for “Azure OpenAI” in the Azure search box. 
Click on “Create” from the menu bar. 
Fill in the following details: 

Subscription : Select your subscription. 
Resource Group : Choose the resource group you just created. 
Region : Specify the region. 
Name : Assign a name to your OpenAI resource. 
Pricing Tier : Select an appropriate pricing tier.

Click “Next Network” and select ‘All networks, including the internet, can access this resource’. 
Proceed by clicking “Next Tags”. 
Finally, click “Create” and then “Submit”. 
Wait a few minutes for the resource to be set up. 

Step 4: Go to Azure AI Studio 

In your Azure dashboard, navigate to Projects Overview and select ‘Chat under Project Playground’. 
Configure your Assistant: 

Role : Assign a role to your bot, from the drop down menu. 
System Message : Provide directives on how the assistant should behave. For example, you could instruct it to adopt the persona of Shakespeare, using rich metaphors and poetic language. 
Examples : Provide user input and expected assistant output, to help your bot learn and respond better. 

Enter a test question for the chatbot: “Write a message to invite friends to my birthday party”. This will help you evaluate your chatbot. 
Select “Deploy to a web app” from “Deploy to” dropdown. 
Choose “Create a new web app” 
Fill the required information and enable the code history in the web app. 
Hit “Deploy”. 

Step 5: Congratulations! 

You have successfully created your assistant! Now, to integrate the chatbot into your website, you can use Python and Flask to connect with the frontend. Here’s how to proceed: 

Retrieve Keys and Endpoints: Use the keys and endpoints from the Azure resource you created earlier. Store these securely in a `.env` file. 
Choose Your Code Editor: Open your preferred code editor to begin coding. 
Refer to Repositories: Check out my repository to know the code. 

Conclusion 

With these steps, you now have a fully functional chatbot powered by Azure OpenAI capabilities. The possibilities are endless, and you can further customize and enhance your assistant as needed. Whether for personal use or business applications, leveraging Azure’s robust AI services opens a world of innovation. Happy coding! 

Resources 

GenAI for Beginners
What is Azure AI Studio ? 
Fundamentals of Azure OpenAI services  
Getting started with Azure OpenAI Assistants  
Azure Samples – OpenAI 
Azure OpenAI Services  

​Microsoft Tech Community – Latest Blogs –Read More 

Microsoft ❤️ Community

The Azure AI Influencers Day Series sparked a wave of collaboration between Microsoft Most Valuable Professionals (MVPs) and Microsoft Learn Student Ambassadors (MLSAs), creating a vibrant tech movement across 10 cities—Gurugram, Pune, Noida, Mumbai, Jaipur, Chandigarh, Andhra Pradesh, Hyderabad, Chennai, and Bengaluru. With 10 offline and 2 online sessions featuring 9 MVPs, 7 Microsoft FTEs, 13 MLSAs, and 7 industry experts, the series drew over 2,328+ attendees.

In a world where technology often seems confined to bustling urban centers, the Azure AI Influencers Day Series stand as a testament to the power of collaboration and innovation. With the support of Azure Developer Community, this series, driven by the passion and expertise of MVPs and MLSAs, transcends geographical barriers to connect students from tier 3 cities with the latest in AI and cloud technologies. 

A Journey Beyond Boundaries 

Imagine students traveling over 500+ kilometers from places like Andhra Pradesh, Trichy, and Chandigarh crossing states to reach the tech hubs of Bengaluru and Noida. For many, this journey was not just a physical relocation but a symbolic leap from their everyday surroundings into the heart of technological innovation. Faculty members played a pivotal role, rallying their students and taking charge of facilitating this adventure. It was not about attending an event; it was about embracing an opportunity that seemed far out of reach from their tier 3 towns. 

Impact on Students and the Community 

The Azure AI Influencers Day Series offered more than just lectures; it provided a hands-on experience with cutting-edge AI tools, sparking excitement and curiosity among attendees. Students like Rakshana, who had never ventured into a major tech city, found inspiration in the exposure to Azure AI’s potential. “Traveling such a long distance was fueled by my passion for technology and a strong desire to expand my knowledge in AI and cloud computing,” Rakshana shared. She left with a deeper understanding of Azure AI, practical insights into its implementation, and valuable connections that will help shape her future in tech. 

For Devansh, a student from a tier 3 city, the series was a revelation. “I realized that geographical boundaries no longer limit access to innovation. The series highlighted how Azure democratizes technology, making it accessible to all. It inspired me to explore new avenues,” he said. This realization was echoed by many, as the series helped students see that their dreams and ambitions were not constrained by where they came from. 

Faculty and Influencer Insights 

From the perspective of faculty like Poornima S, the series was an incredible journey that combined knowledge-sharing, networking, and inspiration. “Watching students and professionals engage with industry experts on topics like Azure, AI, and career development has been immensely rewarding,” she reflected. “The insights shared during these sessions have not only empowered attendees but have also reinforced the importance of staying at the forefront of technology and innovation.” 

For MVPs and MLSAs, the series was an invaluable opportunity to connect with a diverse audience and share the transformative potential of AI. An MSLA, Aditya Shankar Khorne, an MLSA, noted, “The Azure AI Influencer Series played a big role in connecting students with industry trends and real-world AI applications. It offered a hands-on approach, allowing students to engage directly with the latest Azure AI tools and technologies.” Aditya observed that this interaction not only demystified AI for many students but also provided them with the confidence and skills to start their AI journeys. 

A Collaborative Movement 

Each event became a melting pot of ideas, where MVPs and MLSAs not only shared their knowledge but also built bridges between communities. Nanddeep Nachan, an AI & M365 MVP from India (Microsoft Most Valuable Professional), highlighted how the series made advanced AI concepts accessible and relevant to students’ future careers. “I observed that students often struggled with understanding complex AI concepts and practical applications. Initiatives like the Azure AI Influencer Series can address these challenges by providing hands-on learning opportunities, real-world examples, and industry insights to make AI more approachable and relevant to their studies,” Nanddeep shared. 

Students like Monish Mukhari appreciated learning from experts and exploring real-world AI applications. He noted, “The key takeaways were learning about LLM (large language models), RAG, their pricing, and exploring use cases to solve real-world problems. This provided a lot of clarity and helped in understanding the challenges associated with AI technologies.“ 

Building Bridges Between Tier 1 and Tier 3 Cities 

During the Azure AI Influencers Day events in Bangalore and Noida, we were thrilled to see students and participants making significant journeys from Trichy, Andhra Pradesh, and Chandigarh, covering distances of over 500km and 200km respectively, to be part of the sessions. This remarkable turnout was made possible thanks to the dedicated support from MLSAs in each city.

The series also played a crucial role in building bridges between tier 1 and tier 3 cities through technology. It was not about highlighting AI tools—it was about creating an inclusive space where students could network, share, and grow together. Harsith M, attending his first event at a Microsoft office, expressed how impactful the experience was for him. “As an MBA student, it was an inspiring experience to step into a place I’ve always admired since childhood. Visiting Microsoft has been a dream come true, and I hope that one day I’ll have the chance to be part of the Microsoft community!”

Rupam Swain, another student attendee, encapsulated the essence of the series: “Participating in Azure AI Influencer Series broadened my perspective, revealing accessible global opportunities and an inclusive tech ecosystem beyond location barriers.“ 

A Future Beyond Limits 

The Azure AI Influencers Day Series has set a precedent for how technology can unite diverse communities. It is more than an event series; it is a movement that empowers students, educators, and influencers alike to rethink what is possible. By bridging the gap between tier 1 and tier 3 cities, this initiative has given a taste of AI’s potential to students who otherwise might not have had the chance. It’s a celebration of collaboration, of breaking down walls, and of the boundless possibilities that arise when passionate individuals come together to learn, share, and grow. 

As the series continues, it promises to inspire more students and influencers, fostering an inclusive tech ecosystem where everyone, no matter their background or location, can contribute to and shape the future of technology. The Azure AI Influencers Day Series is not just helping communities grow—it’s redefining them, one event at a time. 

A special thanks to our Influencers for being an integral part of the series –Sridharan VenkataRamanan,  Deeksha Sharma, Saurabh Sharma, Manmeet Singh, Saket Kumar, Rajesh Panchal, Vinay Pratap, M.v.k.v Vandana, Bhargavi Chakravarthi Rangarajan, Bran Livinston, Kasam Shaikh, Shrushti Shah, Megha Pandey, Sameer Mhaisekar, Mansun Acharya, Mukesh Kumar Rao, Diya Vijay, Osama Shaikh, Ashish Tiwari, Nilesh Shinde, Viswanatha Swamy, Nandan Vallamdasu, Thirumala Sai Harsha Inumarthi, Dinesh Padhan, Krutam Hathi, Rohit Yadav, Arpita Das, Akshay Prabhat Mishra, Tauqeer Ahmad, Nanddeep Nachan, Smita Nachan, Faizan Akhtar, Harshavardhan Bajoria, Shivam Goyal, Khushi Panwar, Nitinn Asthaana, 

& to our hosting partners – Poornima Institute of Engineering & Technology – Jaipur, Chandigarh University, Dr. D. Y. Patil Institute of Engineering, Management and Research – Akurdi, IEEE Computational Intelligence Society (CIS) CUSB

​Microsoft Tech Community – Latest Blogs –Read More 

Hi Every One

I appreciate your assistance with this issue. The PCs Windows 11 Pro I manage with Intune are not experiencing any problems and are functioning properly. However, there are some PCs that have joined the Local AD where the DLP for endpoints is not working Detect i need know Can Support Client Local AD Join ? I am Onboard local script client Local AD join (Not Config AzureHybrid join on ADDS ) it Can Sync Update but notworking Detach DLP for endpoint I need know it Support for Client Not Ad join ? And Support How to fix & config more ?

​Hi Every One I appreciate your assistance with this issue. The PCs Windows 11 Pro I manage with Intune are not experiencing any problems and are functioning properly. However, there are some PCs that have joined the Local AD where the DLP for endpoints is not working Detect i need know Can Support Client Local AD Join ? I am Onboard local script client Local AD join (Not Config AzureHybrid join on ADDS ) it Can Sync Update but notworking Detach DLP for endpoint I need know it Support for Client Not Ad join ? And Support How to fix & config more ?       Read More

​